What do LLMs need to Synthesize Correct Router Configurations?
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
We investigate whether Large Language Models (e.g., GPT-4) can synthesize correct router configurations with reduced manual effort. We find GPT-4 works very badly by itself, producing promising draft configurations but with egregious errors in topology, syntax, and semantics. Our strategy, that we call Verified Prompt Programming, is to combine GPT-4 with verifiers, and use localized feedback from the verifier to automatically correct errors. Verification requires a specification and actionable localized feedback to be effective. We show results for two use cases: translating from Cisco to Juniper configurations on a single router, and implementing a no-transit policy on multiple routers. While human input is still required, if we define the leverage as the number of automated prompts to the number of human prompts, our experiments show a leverage of 10X for Juniper translation, and 6X for implementing the no-transit policy, ending with verified configurations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526
Evaluating Large Language Models Trained on Code
Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H. P. D. O., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al. (2021) · arXiv · doi:10.48550/arxiv.2107.03374 · Cited by 1,436
Competition-level code generation with AlphaCode
Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., Eccles, T., Keeling, J., Gimeno, F., Dal Lago, A., et al. (2022) · Science · doi:10.1126/science.abq1158 · Cited by 1,043
Competition-Level Code Generation with AlphaCode
Li, Y., Choi, D., Chung, J., Kushman, N., Schrittwieser, J., Leblond, R., Eccles, T., Keeling, J., Gimeno, F., Lago, A. D., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.07814 · Cited by 1,043
Cited by
Clover: Closed-Loop Verifiable Code Generation
Sun, C., Sheng, Y., Padon, O., & Barrett, C. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-65112-0_7 · Cited by 43
Clover: Closed-Loop Verifiable Code Generation
Sun, C., Sheng, Y., Padon, O., & Barrett, C. (2023) · arXiv · doi:10.48550/arxiv.2310.17807 · Cited by 43
“Research in specific domains includes examples like [45], which proposes a framework for porting C to Checked-C to enable memory safety for C programs, and [46], which uses LLMs to synthesize verified router configurations in networking.”
MethodIntent-driven network management with multi-agent LLMs: the confucius framework
Wang, Z., Lin, S., Yan, G., Ghorbani, S., Yu, M., Zhou, J., Hu, N., Baruah, L., Peters, S., Kamath, S., et al. (2025) · Proceedings of the ACM SIGCOMM 2025 Conference · doi:10.1145/3718958.3750537 · Cited by 27
“Mani et al. [35] use LLMs to generate graph manipulation code for topology management, and Mondal et al. [39] apply LLMs to synthesize router configurations.”
Localized explanations for automatically synthesized network configurations
Nazari, A., Zhang, Y., Raghothaman, M., & Chen, H. (2024) · Proceedings of the 23rd ACM Workshop on Hot Topics in Networks · doi:10.1145/3696348.3696888 · Cited by 5
Tackling ambiguity in user intent for LLM-based network configuration synthesis
Mondal, R., Bjorner, N., Millstein, T., Tang, A., & Varghese, G. (2025) · Proceedings of the 24th ACM Workshop on Hot Topics in Networks · doi:10.1145/3772356.3772402 · Cited by 2
Self-citation
Metadata
- Authors
- Mondal, R., Tang, A., Beckett, R., Millstein, T., & Varghese, G.
- Venue
- Proceedings of the 22nd ACM Workshop on Hot Topics in Networks
- Publisher
- ACM
- Published
- 2023-11-28
- Pages
- 189-195
- OpenAlex
- W4388629193
- Cited by
- 90
- References
- 5
- FWCI
- 23.98
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.